English
Related papers

Related papers: Embarrassingly Shallow Autoencoders for Sparse Dat…

200 papers

Learning recommender systems with multi-class optimization objective is a prevalent setting in recommendation. However, as observed user feedback often accounts for a tiny fraction of the entire item pool, the standard Softmax loss tends to…

Information Retrieval · Computer Science 2024-10-10 Hao Zhang , Mingyue Cheng , Qi Liu , Yucong Luo , Rui Li , Enhong Chen

We study parameter estimation in Nonlinear Factor Analysis (NFA) where the generative model is parameterized by a deep neural network. Recent work has focused on learning such models using inference (or recognition) networks; we identify a…

Machine Learning · Statistics 2017-10-18 Rahul G. Krishnan , Dawen Liang , Matthew Hoffman

Recent research has revealed that deep neural networks often take dataset biases as a shortcut to make decisions rather than understand tasks, leading to failures in real-world applications. In this study, we focus on the spurious…

Computation and Language · Computer Science 2023-06-23 Yanrui Du , Jing Yan , Yan Chen , Jing Liu , Sendong Zhao , Qiaoqiao She , Hua Wu , Haifeng Wang , Bing Qin

Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional approaches to analyzing SAEs typically rely solely on…

Machine Learning · Computer Science 2025-09-24 Dong Shu , Xuansheng Wu , Haiyan Zhao , Mengnan Du , Ninghao Liu

Sparse autoencoders (SAEs) have shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models, demonstrating their…

Machine Learning · Computer Science 2024-08-06 Charles O'Neill , Christine Ye , Kartheik Iyer , John F. Wu

Training machine learning models with the only accuracy as a final goal may promote prejudices and discriminatory behaviors embedded in the data. One solution is to learn latent representations that fulfill specific fairness metrics.…

Machine Learning · Computer Science 2021-07-28 Patrik Joslin Kenfack , Adil Mehmood Khan , Rasheed Hussain , S. M. Ahsan Kazmi

In this book chapter, we discuss recent advances in data-driven approaches for inverse problems. In particular, we focus on the \emph{paired autoencoder} framework, which has proven to be a powerful tool for solving inverse problems in…

Machine Learning · Computer Science 2025-08-20 Matthias Chung , Bas Peters , Michael Solomon

Language modeling on large-scale datasets leads to impressive performance gains on various downstream language tasks. The validation pre-training loss (or perplexity in autoregressive language modeling) is often used as the evaluation…

Machine Learning · Computer Science 2022-10-26 Hong Liu , Sang Michael Xie , Zhiyuan Li , Tengyu Ma

Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal…

Computation and Language · Computer Science 2025-02-27 Sumanta Bhattacharyya , Pedram Rooshenas

With the widespread adoption of information systems, recommender systems are widely used for better user experience. Collaborative filtering is a popular approach in implementing recommender systems. Yet, collaborative filtering methods are…

Information Retrieval · Computer Science 2019-08-20 Sapumal Ahangama , Danny Chiang-Choon Poo

Acquiring and training on large-scale labeled data can be impractical due to cost constraints. Additionally, the use of small training datasets can result in considerable variability in model outcomes, overfitting, and learning of spurious…

Machine Learning · Computer Science 2025-07-08 Jiashu Tao , Reza Shokri

Learning from implicit user feedback is challenging as we can only observe positive samples but never access negative ones. Most conventional methods cope with this issue by adopting a pairwise ranking approach with negative sampling.…

Information Retrieval · Computer Science 2021-01-20 Riku Togashi , Masahiro Kato , Mayu Otani , Shin'ichi Satoh

Active learning enables efficient model training by leveraging interactions between machine learning agents and human annotators. We study and propose a novel framework that formulates batch active learning from the sparse approximation's…

Machine Learning · Computer Science 2022-11-08 Maohao Shen , Bowen Jiang , Jacky Yibo Zhang , Oluwasanmi Koyejo

Sparse expert models are a thirty-year old concept re-emerging as a popular architecture in deep learning. This class of architecture encompasses Mixture-of-Experts, Switch Transformers, Routing Networks, BASE layers, and others, all with…

Machine Learning · Computer Science 2022-09-07 William Fedus , Jeff Dean , Barret Zoph

Shapelets are discriminative subsequences (or shapes) with high interpretability in time series classification. Due to the time-intensive nature of shapelet discovery, existing shapelet-based methods mainly focus on selecting discriminative…

Machine Learning · Computer Science 2025-06-04 Zhen Liu , Yicheng Luo , Boyuan Li , Emadeldeen Eldele , Min Wu , Qianli Ma

In a standard classification framework a set of trustworthy learning data are employed to build a decision rule, with the final aim of classifying unlabelled units belonging to the test set. Therefore, unreliable labelled observations,…

Applications · Statistics 2019-11-20 Andrea Cappozzo , Francesca Greselin , Thomas Brendan Murphy

Disentangling model activations into meaningful features is a central problem in interpretability. However, the absence of ground-truth for these features in realistic scenarios makes validating recent approaches, such as sparse dictionary…

Machine Learning · Computer Science 2024-05-21 Aleksandar Makelov , George Lange , Neel Nanda

Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, controllable concepts. On the one hand, these approaches…

Machine Learning · Computer Science 2026-03-03 Shruti Joshi , Andrea Dittadi , Sébastien Lachapelle , Dhanya Sridhar

This paper solves the sparsest feedback selection problem for linear time invariant structured systems, a long-standing open problem in structured systems. We consider structurally cyclic systems with dedicated inputs and outputs. We prove…

Optimization and Control · Mathematics 2017-09-26 Shana Moothedath , Prasanna Chaporkar , Madhu N. Belur

We investigate data filtering for large model pretraining via new scaling studies that target the high compute, data-scarce regime. In spite of an apparently common belief that filtering data to include only high-quality information is…

Machine Learning · Computer Science 2026-05-20 Christopher Mohri , John Duchi , Tatsunori Hashimoto
‹ Prev 1 8 9 10 Next ›